© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 35032
    Prev
    Next
    INDEX
    Explanations

    abstract and generic concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ppin
    0.46
    밧
    0.39
    ചന
    0.38
    myfaces
    0.38
    fortunately
    0.38
    ত
    0.37
    netics
    0.37
    ᾷ
    0.37
     repente
    0.36
    viewDidLoad
    0.36
    POSITIVE LOGITS
     abstract
    1.36
     generic
    1.28
     Generic
    1.26
    abstract
    1.24
    generic
    1.15
    Generic
    1.13
    抽象
    1.12
     general
    1.09
     Abstract
    1.08
     абстра
    1.08
    Activations Density 0.001%

    No Known Activations